正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Many 3D generators output Gaussian Splats (3DGS) for fast rendering, flexible deployment, and high visual fidelity. Static 3DGS aren't world models (no dynamics/semantics) but a true world model must allow distilling 3D-consistent representations for any given time step (3DGS/meshes). This post-distillation serves a dual purpose: 1) validates physical consistency... show more

Matthias Niessner

50,179 subscribers

26,486 次观看 • 7 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Echo-2 is a physically-grounded world model from which we can distill meshes, point clouds, or 3DGS scene representations. Directly usable in a myriad of downstream applications from gaming to training robots. Want to build your own world? Try it here:

Echo-2 is a physically-grounded world model from which we can distill meshes, point clouds, or 3DGS scene representations. Directly usable in a myriad of downstream applications from gaming to training robots. Want to build your own world? Try it here:

SpAItial AI

21,668 次观看 • 6 个月前

Beyond photos/videos, what's the next medium for sharing visual experiences? 🤔 NeRF/3DGS are great but only capture a static 3D world and ignore ambient scene dynamics. In this paper, we show how we can reconstruct/render these essential scene elements even with a single causal video.

Beyond photos/videos, what's the next medium for sharing visual experiences? 🤔 NeRF/3DGS are great but only capture a static 3D world and ignore ambient scene dynamics. In this paper, we show how we can reconstruct/render these essential scene elements even with a single causal video.

Jia-Bin Huang

28,781 次观看 • 2 年前

🧊 Splats → Voxels: Bridging 3D Gaussian Splatting with Dynamic Voxels World Labs Just added this last tool to the GS editor plug-in that can convert any 3DGS splats into interactive voxel worlds with full physics support! 🚀 3 Rendering Modes: 🔵 CPU Mode - GameObjects for each voxel. Max physics interaction, perfect for destructible environments 🟢 GPU Mode - DrawMeshInstancedIndirect. Renders 100K+ voxels at 90fps. Pure visual, no physics overhead 🟡 Hybrid Mode - Best of both! GPU renders distant voxels Building this so you can literally punch through a GS World and watch it crumble 🥊 #GaussianSplatting #unity3d #GameDev #VR #3DGS #Voxels #Physics #madewithunity

🧊 Splats → Voxels: Bridging 3D Gaussian Splatting with Dynamic Voxels World Labs Just added this last tool to the GS editor plug-in that can convert any 3DGS splats into interactive voxel worlds with full physics support! 🚀 3 Rendering Modes: 🔵 CPU Mode - GameObjects for each voxel. Max physics interaction, perfect for destructible environments 🟢 GPU Mode - DrawMeshInstancedIndirect. Renders 100K+ voxels at 90fps. Pure visual, no physics overhead 🟡 Hybrid Mode - Best of both! GPU renders distant voxels Building this so you can literally punch through a GS World and watch it crumble 🥊 #GaussianSplatting #unity3d #GameDev #VR #3DGS #Voxels #Physics #madewithunity

Daniel Skaale

29,183 次观看 • 10 个月前

Distilled-3DGS Distilled 3D Gaussian Splatting

Distilled-3DGS Distilled 3D Gaussian Splatting

AK

14,666 次观看 • 1 年前

EDGS: Eliminating Densification for Efficient Convergence of 3DGS Contributions: • We show that initial triangulation based on 2D correspondences can replace the incremental refinement process, fundamentally changing how 3DGS models allocate resources. • Our method reduces the path each Gaussian must travel in parameter space. Careful initialization not only accelerates convergence but also guides optimization toward a convergence point corresponding to lower reconstruction error and thus higher reconstruction quality. • Our approach outperforms both speed-optimized and quality-focused state-of-the-art models while using only half the splats of standard 3DGS. By improving initialization rather than altering the optimization process, this method is compatible with other 3DGS acceleration techniques, making it a flexible enhancement to existing models.

EDGS: Eliminating Densification for Efficient Convergence of 3DGS Contributions: • We show that initial triangulation based on 2D correspondences can replace the incremental refinement process, fundamentally changing how 3DGS models allocate resources. • Our method reduces the path each Gaussian must travel in parameter space. Careful initialization not only accelerates convergence but also guides optimization toward a convergence point corresponding to lower reconstruction error and thus higher reconstruction quality. • Our approach outperforms both speed-optimized and quality-focused state-of-the-art models while using only half the splats of standard 3DGS. By improving initialization rather than altering the optimization process, this method is compatible with other 3DGS acceleration techniques, making it a flexible enhancement to existing models.

MrNeRF

125,025 次观看 • 1 年前

The context size of video world models is only a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. 1/3

The context size of video world models is only a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. 1/3

Gordon Wetzstein

35,137 次观看 • 1 年前

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Bilawal Sidhu

92,927 次观看 • 2 年前

Arnold can now import, relight and render 3D Gaussian Splats Check out the other new features in the renderer, including updates to toon shading and experimental free cloud rendering service Flow Render #ArnoldRenderer #3DGS #VFX Arnold

Arnold can now import, relight and render 3D Gaussian Splats Check out the other new features in the renderer, including updates to toon shading and experimental free cloud rendering service Flow Render #ArnoldRenderer #3DGS #VFX Arnold

CG Channel

19,289 次观看 • 4 个月前

Photos to 3D model with 2Xplat. Pose-free 3D Gaussian Splatting - 0.15s–0.31s inference; - beats YoNoSplat; - high-fidelity splats

Photos to 3D model with 2Xplat. Pose-free 3D Gaussian Splatting - 0.15s–0.31s inference; - beats YoNoSplat; - high-fidelity splats

Wildminder

23,565 次观看 • 7 个月前

Meet 3D Gaussian Splatting - a 3D AI breakthrough that’s changing the game for real-time 3D rendering. It generates 3D world with state-of-the-art visuals at fast speeds: 100+ fps at 1080p. Here’s the magic behind it:

Meet 3D Gaussian Splatting - a 3D AI breakthrough that’s changing the game for real-time 3D rendering. It generates 3D world with state-of-the-art visuals at fast speeds: 100+ fps at 1080p. Here’s the magic behind it:

el.cine

60,197 次观看 • 1 年前

better gaussian splatting? 50K planar splats, 32 bytes each, 1.2mb lossless scene file, ~35 dB PSNR against test views, fast real-time rendering compare with vanilla 3DGS: 300K+ primitives, 236 bytes per primitive, 74 MB file (from

better gaussian splatting? 50K planar splats, 32 bytes each, 1.2mb lossless scene file, ~35 dB PSNR against test views, fast real-time rendering compare with vanilla 3DGS: 300K+ primitives, 236 bytes per primitive, 74 MB file (from

Matt DesLauriers

14,021 次观看 • 3 个月前

A high magnification Gaussian splat, of the edge of three-ply toilet paper (unused). #3dgs

A high magnification Gaussian splat, of the edge of three-ply toilet paper (unused). #3dgs

Dany Bittel

10,445 次观看 • 3 个月前

Human Hair Reconstruction with Strand-Aligned 3D Gaussians Contributions (cited): – We propose a new 3D line lifting scheme that uses a modified 3DGS reconstruction technique to lift 2D orientation maps into a 3D field while also providing refinement of the camera parameters; – We introduce a dual representation of hair strand polylines and 3D Gaussians to achieve differentiable rasterization of hair strands and leverage photometric constraints for strand-based hair reconstruction; – Based on these components, we propose a coarse-to-fine optimization method for prior-guided hair reconstruction that leverages both latent and explicit representations of the hairstyle.

Human Hair Reconstruction with Strand-Aligned 3D Gaussians Contributions (cited): – We propose a new 3D line lifting scheme that uses a modified 3DGS reconstruction technique to lift 2D orientation maps into a 3D field while also providing refinement of the camera parameters; – We introduce a dual representation of hair strand polylines and 3D Gaussians to achieve differentiable rasterization of hair strands and leverage photometric constraints for strand-based hair reconstruction; – Based on these components, we propose a coarse-to-fine optimization method for prior-guided hair reconstruction that leverages both latent and explicit representations of the hairstyle.

MrNeRF

106,724 次观看 • 2 年前

Procedural Gaussian Splats in PlayCanvas 🔥 Everything becomes splats: Images. Text. Lines. One unified render, seamlessly blending with 3DGS models.

Procedural Gaussian Splats in PlayCanvas 🔥 Everything becomes splats: Images. Text. Lines. One unified render, seamlessly blending with 3DGS models.

Martin Valigursky

19,026 次观看 • 9 个月前

(1/2) Check out "𝐏𝐨𝐥𝐲𝐃𝐢𝐟𝐟: Generating 3D Polygonal Meshes with Diffusion Models"! Our model operates directly on the polygons of 3D meshes and generates novel shapes as output through an iterative diffusion process.

(1/2) Check out "𝐏𝐨𝐥𝐲𝐃𝐢𝐟𝐟: Generating 3D Polygonal Meshes with Diffusion Models"! Our model operates directly on the polygons of 3D meshes and generates novel shapes as output through an iterative diffusion process.

Matthias Niessner

57,973 次观看 • 2 年前

F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Consistent Gaussian Splatting Contributions: • We pioneer 3D-aware generation using generalizable feed-forward Gaussian Splatting representation, achieving significant efficiency and favorable rendering quality on monocular datasets. • We significantly advance the capability of pixel-aligned Gaussian Splatting representations by designing a self-supervised cycle training strategy specifically tailored for monocular datasets. • We further mitigate the artifacts of 3D-aware representations caused by large viewpoint shifts by introducing geometry-aware video priors.

F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Consistent Gaussian Splatting Contributions: • We pioneer 3D-aware generation using generalizable feed-forward Gaussian Splatting representation, achieving significant efficiency and favorable rendering quality on monocular datasets. • We significantly advance the capability of pixel-aligned Gaussian Splatting representations by designing a self-supervised cycle training strategy specifically tailored for monocular datasets. • We further mitigate the artifacts of 3D-aware representations caused by large viewpoint shifts by introducing geometry-aware video priors.

MrNeRF

14,229 次观看 • 1 年前

🔥Happy New Year all! 🧨 In 2026 Splats will be like pixels! Ultra dense 3D Gaussian Splatting VFX Backdrops! In 360° → 3DGS pipeline >8M splats per scene Zero compromises on detail! Every surface. Every edge. Every reflection. This is what photorealism should look like:-) #GaussianSplatting #unity3d #GameDev #VR #3DGS #Physics #madewithunity

🔥Happy New Year all! 🧨 In 2026 Splats will be like pixels! Ultra dense 3D Gaussian Splatting VFX Backdrops! In 360° → 3DGS pipeline >8M splats per scene Zero compromises on detail! Every surface. Every edge. Every reflection. This is what photorealism should look like:-) #GaussianSplatting #unity3d #GameDev #VR #3DGS #Physics #madewithunity

Daniel Skaale

16,806 次观看 • 10 个月前

PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics paper page: introduce PhysGaussian, a new method that seamlessly integrates physically grounded Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis. Employing a custom Material Point Method (MPM), our approach enriches 3D Gaussian kernels with physically meaningful kinematic deformation and mechanical stress attributes, all evolved in line with continuum mechanics principles. A defining characteristic of our method is the seamless integration between physical simulation and visual rendering: both components utilize the same 3D Gaussian kernels as their discrete representations. This negates the necessity for triangle/tetrahedron meshing, marching cubes, "cage meshes," or any other geometry embedding, highlighting the principle of "what you see is what you simulate (WS^2)." Our method demonstrates exceptional versatility across a wide variety of materials--including elastic entities, metals, non-Newtonian fluids, and granular materials--showcasing its strong capabilities in creating diverse visual content with novel viewpoints and movements.

PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics paper page: introduce PhysGaussian, a new method that seamlessly integrates physically grounded Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis. Employing a custom Material Point Method (MPM), our approach enriches 3D Gaussian kernels with physically meaningful kinematic deformation and mechanical stress attributes, all evolved in line with continuum mechanics principles. A defining characteristic of our method is the seamless integration between physical simulation and visual rendering: both components utilize the same 3D Gaussian kernels as their discrete representations. This negates the necessity for triangle/tetrahedron meshing, marching cubes, "cage meshes," or any other geometry embedding, highlighting the principle of "what you see is what you simulate (WS^2)." Our method demonstrates exceptional versatility across a wide variety of materials--including elastic entities, metals, non-Newtonian fluids, and granular materials--showcasing its strong capabilities in creating diverse visual content with novel viewpoints and movements.

AK

96,291 次观看 • 3 年前